Comparative Technical and Volatility Analysis of Microsoft, Amazon, and NVIDIA Stocks

symbols <- c("MSFT", "AMZN", "NVDA")
start_date <- Sys.Date() - 180
end_date <- Sys.Date()

get_stock_data <- function(symbol) {
  stock <- getSymbols(symbol, src = "yahoo", from = start_date, to = end_date, auto.assign = FALSE)
  stock_df <- data.frame(Date = index(stock), coredata(stock))
  colnames(stock_df) <- c("Date", "Open", "High", "Low", "Close", "Volume", "Adjusted")
  
  stock_df <- stock_df %>%
    mutate(
      DailyReturn = c(NA, diff(Adjusted) / lag(Adjusted, 1)[-1]),
      MA5 = SMA(Adjusted, 5),
      MA20 = SMA(Adjusted, 20),
      MA50 = SMA(Adjusted, 50)
    )
  
  bb <- BBands(stock_df$Adjusted, n = 20)
  stock_df <- cbind(stock_df, bb[, c("up", "dn")])
  stock_df$Symbol <- symbol
  
  return(stock_df)
}

all_stocks <- lapply(symbols, get_stock_data)
all_stocks_df <- do.call(rbind, all_stocks)

create_candlestick <- function(stock_df, symbol) {
  df <- stock_df %>% filter(Symbol == symbol)
  
  p <- plot_ly(data = df, type = "candlestick",
          x = ~Date, open = ~Open, close = ~Close,
          high = ~High, low = ~Low, name = "Price") %>%
    add_lines(x = ~Date, y = ~MA5, name = "5-day MA", line = list(color = 'blue')) %>%
    add_lines(x = ~Date, y = ~MA20, name = "20-day MA", line = list(color = 'orange')) %>%
    add_lines(x = ~Date, y = ~MA50, name = "50-day MA", line = list(color = 'green')) %>%
    add_lines(x = ~Date, y = ~up, name = "Upper BB", line = list(color = 'purple', dash = "dot")) %>%
    add_lines(x = ~Date, y = ~dn, name = "Lower BB", line = list(color = 'purple', dash = "dot")) %>%
    layout(title = paste(symbol, "Stock Price"),
           xaxis = list(title = "Date"),
           yaxis = list(title = "Price (USD)"),
           legend = list(orientation = "h", x = 0.5, y = 1.05, xanchor = "center"))
  
  return(p)
}

create_candlestick(all_stocks_df, "MSFT")

create_candlestick(all_stocks_df, "AMZN")

create_candlestick(all_stocks_df, "NVDA")

returns_df <- all_stocks_df %>%
  select(Date, Symbol, DailyReturn) %>%
  na.omit()

risk_free_rate <- 0.01 / 252  # Daily risk-free rate

summary_stats <- returns_df %>%
  group_by(Symbol) %>%
  summarize(
    Mean_Return = mean(DailyReturn),
    Std_Dev = sd(DailyReturn),
    Min_Return = min(DailyReturn),
    Max_Return = max(DailyReturn)
  ) %>%
  mutate(
    Sharpe_Ratio = (Mean_Return - risk_free_rate) / Std_Dev
  )

summary_stats

## # A tibble: 3 × 6
##   Symbol Mean_Return Std_Dev Min_Return Max_Return Sharpe_Ratio
##   <chr>        <dbl>   <dbl>      <dbl>      <dbl>        <dbl>
## 1 AMZN      0.000365  0.0246    -0.0898      0.120       0.0132
## 2 MSFT      0.000896  0.0192    -0.0618      0.101       0.0445
## 3 NVDA      0.000598  0.0399    -0.170       0.187       0.0140

plot_ly(summary_stats, x = ~Symbol, y = ~Std_Dev, type = 'bar',
        marker = list(color = 'tomato')) %>%
  layout(title = "Volatility Comparison",
         xaxis = list(title = "Stock"),
         yaxis = list(title = "Standard Deviation of Daily Return"))

most_volatile <- summary_stats %>%
  filter(Std_Dev == max(Std_Dev)) %>%
  pull(Symbol)

cat("👉 Most volatile stock in this period:", most_volatile)

## 👉 Most volatile stock in this period: NVDA

plot_ly() %>%
  add_histogram(data = filter(returns_df, Symbol == "MSFT"), x = ~DailyReturn, name = "MSFT", opacity = 0.6) %>%
  add_histogram(data = filter(returns_df, Symbol == "AMZN"), x = ~DailyReturn, name = "AMZN", opacity = 0.6) %>%
  add_histogram(data = filter(returns_df, Symbol == "NVDA"), x = ~DailyReturn, name = "NVDA", opacity = 0.6) %>%
  layout(title = "Distribution of Daily Returns",
         barmode = "overlay",
         xaxis = list(title = "Daily Return"),
         yaxis = list(title = "Frequency"))

# Density Plot of Daily Returns
densities <- returns_df %>%
  group_by(Symbol) %>%
  summarize(density_data = list(density(DailyReturn, na.rm = TRUE)), .groups = "drop") %>%
  mutate(
    x = lapply(density_data, function(d) d$x),
    y = lapply(density_data, function(d) d$y)
  ) %>%
  select(Symbol, x, y) %>%
  unnest(cols = c(x, y))

plot_ly(data = densities, x = ~x, y = ~y, color = ~Symbol, type = 'scatter', mode = 'lines') %>%
  layout(title = "Density of Daily Returns",
         xaxis = list(title = "Daily Return"),
         yaxis = list(title = "Density"))

cat("### 📈 Summary of Findings\n",
    "- **", most_volatile, "** exhibited the highest volatility over the past 180 days.\n",
    "- Candlestick charts help visualize price trends and technical indicators.\n",
    "- Density plots reveal return distribution patterns and help compare risk.\n",
    "- Volatility plot shows relative risk across the analyzed stocks.\n", sep = "")

## ### 📈 Summary of Findings
## - **NVDA** exhibited the highest volatility over the past 180 days.
## - Candlestick charts help visualize price trends and technical indicators.
## - Density plots reveal return distribution patterns and help compare risk.
## - Volatility plot shows relative risk across the analyzed stocks.